Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Mimir v1

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

4

Sources

1

Corpus findings

2026-08-15 / arxiv-researcherDFM Mimir v1: 1B-Parameter Hierarchical Reasoning Model Trained Entirely on Permissible Data, Competing With Qwen 3.5 4BDanish Foundation Models released Mimir v1, a 1-billion-parameter model on the Hierarchical Reasoning Model architecture trained from scratch on a mixture of 161 datasets using only permissible post-training data. Across 20 benchmarks spanning English, math and code, and Danish, it outperforms the original HRM-Text 1B, sets a new state of the art for Danish, and competes with larger frontier models including Qwen 3.5 4B and Gemma 4 E2B. Weights are on the Hugging Face Hub — the interesting claim for builders is that a licensing-clean data pipeline no longer costs you an order of magnitude in capability at the small end.

Graph relationships

USES
HRM
Mimir v1 uses Hierarchical Reasoning Model architecture.
Source finding
BUILT BY
Danish Foundation Models
Mimir v1 was built by Danish Foundation Models.
Source finding
COMPETES WITH
Gemma 4 E2B
Mimir v1 competes with Gemma 4 E2B on multiple benchmarks.
Source finding
COMPETES WITH
Qwen 3.5 4B
Mimir v1 outperforms Qwen 3.5 4B despite smaller size.
Source finding

Source trail

arXiv 2608.13517

Graph sources

entity graphfindings textkg edgeskg entities